Complex Underwater Environment Research Articles

Ship-Radiated Noise Separation in Underwater Acoustic Environments Using a Deep Time-Domain Network

Ship-radiated noise separation is critical in both military and economic domains. However, due to the complex underwater environments with multiple noise sources and reverberation, separating ship-radiated noise poses a significant challenge. Traditionally, underwater acoustic signal separation has employed blind source separation methods based on independent component analysis. Recently, the separation of underwater acoustic signals has been approached as a deep learning problem. This involves learning the features of ship-radiated noise from training data. This paper introduces a deep time-domain network for ship-radiated noise separation by leveraging the power of parallel dilated convolution and group convolution. The separation layer employs parallel dilated convolution operations with varying expansion factors to better extract low-frequency features from the signal envelope while preserving detailed information. Additionally, we use group convolution to reduce the expansion of network size caused by parallel convolution operations, enabling the network to maintain a smaller size and computational complexity while achieving good separation performance. The proposed approach is demonstrated to be superior to the other common networks in the DeepShip dataset through comprehensive comparisons.

Decoupled variational retinex for reconstruction and fusion of underwater shallow depth-of-field image with parallax and moving objects

Underwater imaging often suffers from poor quality due to the complex underwater environment and limitations of hardware equipment, leading to images with shallow depth of field and moving objects, which pose a challenge for information fusion of image sequences from the same underwater scene. To effectively address these problems, we propose a decoupled variational Retinex method for reconstructing and fusing underwater shallow depth of field images. Specifically, we first construct a module that adopts the decoupled variational Retinex model to adjust pixel dynamic range and luminance components, enhance non-local properties’ extraction with higher-order data constraints, and significantly improve image quality. Then, we develop a precision alignment strategy for image sequences by calculating and correcting control point deviations in the overlapping areas, achieving accurate registration of the image sequences, and effectively reconstructing scenes with parallax. Moreover, scenes with moving objects within the image sequence are reconstructed by redistributing overlapping areas. We design a novel cost function based on the neighborhood information of seams, which facilitates iterative optimization of these solved seams. This process improves the segmentation accuracy within these regions, achieving more precise scene reconstruction. Compared with state-of-the-art approaches, our method demonstrates superior performance in rectifying degraded image quality and reconstructing visually appealing images, with the resulting reconstructed images showing enhanced subjective visual quality.

DDformer: Dimension decomposition transformer with semi-supervised learning for underwater image enhancement

Vision-guided Autonomous Underwater Vehicles (AUVs) have gradually become significant tools for human exploration of the ocean. However, distorted images severely limit the visual ability, making it difficult to meet the needs of complex underwater environment perception. Fortunately, recent advancements in deep learning have led to rapid developments in underwater image enhancement. The emergence of the Transformer architecture has further enhanced the capabilities of deep learning. However, the direct application of Transformer to underwater image enhancement presents challenges in computing pixel-level global information and extracting local features. In this paper, we present a novel approach that merges dimension decomposition Transformer with semi-supervised learning for underwater image enhancement. To begin, dimension decomposition attention is proposed, which enables Transformer to compute global dependencies directly at the original scale and correct color distortions effectively. Concurrently, we employ convolutional neural networks to compensate for Transformer's limitations in extracting local features, thereby enriching details and textures. Subsequently, a multi-stage Transformer strategy is introduced to divide the network into high- and low-resolution stages for multi-scale global information extraction. It helps correct color distortions while enhancing the network's focus on regions with severe degradation. Moreover, we design a semi-supervised learning framework to reduce the reliance on paired datasets and construct a corresponding multi-scale fusion discriminator to enhance the sensitivity to input data. Experimental results demonstrate that our method outperforms state-of-the-art approaches, showcasing excellent learning and generalization capabilities on subjective perception and overall evaluation metrics. Furthermore, outstanding results highlight the significant improvements it brings to downstream visual engineering applications. The code of the proposed DDformer is available at https://github.com/ZhiGao-hfuu/DDformer.

EF-UODA: Underwater Object Detection Based on Enhanced Feature

The ability to detect underwater objects accurately is important in marine environmental engineering. Although many kinds of underwater object detection algorithms with relatively high accuracy have been proposed, they involve a large number of parameters and floating point operations (FLOPs), and often fail to yield satisfactory results in complex underwater environments. In light of the demand for an algorithm with the capability to extract high-quality features in complex underwater environments, we proposed a one-stage object detection algorithm called the enhanced feature-based underwater object detection algorithm (EF-UODA), which was based on the architecture of Next-ViT, the loss function of YOLOv8, and Ultralytics. First, we developed a highly efficient module for convolutions, called efficient multi-scale pointwise convolution (EMPC). Second, we proposed a feature pyramid architecture called the multipath fast fusion-feature pyramid network (M2F-FPN) based on different modes of feature fusion. Finally, we integrated the Next-ViT and the minimum point distance intersection over union loss functions in our proposed algorithm. Specifically, on the URPC2020 dataset, EF-UODA surpasses the state-of-the-art (SOTA) convolution-based object detection algorithm YOLOv8X by 2.9% mean average precision (mAP), and surpasses the SOTA ViT-based object detection algorithm real-time detection transformer (RT-DETR) by 2.1%. Meanwhile, it achieves the lowest FLOPs and parameters. The results of extensive experiments showed that EF-UODA had excellent feature extraction capability, and was adequately balanced in terms of the number of FLOPs and parameters.

YOLO‐UOD: An underwater small object detector via improved efficient layer aggregation network

AbstractAccurate detection of underwater objects is a key indicator technology to effectively enhance the field of marine development and application, and is of great importance to various fields including marine military defense and seafood aquaculture. Efficient and rapid detection of underwater targets is a crucial technological challenge in this field. To meet the challenges posed by these issues, this study applies the convolutional omni‐efficient layer aggregation network (CO‐ELAN) module to the detector backbone to improve the ability of the network structure to acquire underwater objects from image information. The module improves the feature representation of gradient branching through a multi‐dimensional dynamic convolution and attention mechanism. In terms of loss calculation, the optimized normalized Wasserstein distance approach is used to predict the box distribution probabilistic modelling method to determine comparable distances to the ground box and obtain better samples of small target labels. Here, an underwater image enhancement algorithm based on white balance and underwater blur fusion is used to obtain clear images that enable improved detector performance. After the verification experiment on the URPC2018 dataset, it is found that the detector has better underwater detection ability compared with other detectors in the complex underwater environment. The proposed method achieves a 2.4% improvement over the YOLOv7 baseline model, while reducing computation costs by 5%.

An Obstacle Avoidance Strategy for AUV Based on State-Tracking Collision Detection and Improved Artificial Potential Field

This paper proposes a fusion algorithm based on state-tracking collision detection and the simulated annealing potential field (SCD-SAPF) to address the challenges of obstacle avoidance for autonomous underwater vehicles (AUVs) in dynamic environments. Navigating AUVs in complex underwater environments requires robust autonomous obstacle avoidance capabilities. The SCD-SAPF algorithm aims to accurately assess collision risks and efficiently plan avoidance trajectories. The algorithm introduces an SCD model for proactive collision risk assessment, predicting collision risks between AUVs and dynamic obstacles. Additionally, it proposes a simulated annealing (SA) algorithm to optimize trajectory planning in a simulated annealing potential field (SAPF), integrating the SCD model with the SAPF algorithm to guide AUVs in obstacle avoidance by generating optimal heading and velocity outputs. Extensive simulation experiments demonstrate the effectiveness and robustness of the algorithm in various dynamic scenarios, enabling the early avoidance of dynamic obstacles and outperforming traditional methods. This research provides an accurate collision risk assessment and efficient obstacle avoidance trajectory planning, offering an innovative approach to the field of underwater robotics and supporting the enhancement of AUV autonomy and reliability in practical applications.

Precise underwater fish measurement: A geometric approach leveraging medium regression

Accurate estimation of fish length is crucial aquaculture processes. Precise and real-time estimation of fish length aids fish farmers in formulating effective farming strategies. Existing methods for estimating the length of underwater fish have made significant advancements in overcoming the interferences present in complex underwater environments. Nevertheless, the measurement results of some methods continue to be limited by variations in the refractive index of multiple media and deviations in imaging angles, resulting in measurement errors and diminished practicality. Consequently, we propose a measurement method that aims to address the aforementioned challenges in fisheries aquaculture by providing more accurate and cost-effective solutions. This method initially introduces the concept of regressing multiple media into a single medium to correct underwater depth estimation and enhance underwater imaging quality. Subsequently, an accurate plane fitting algorithm is applied to precisely fit the fish body plane and extract its corresponding normal vector information. Finally, taking into account the light propagation path and accounting for the limitations of precise values, we utilize the geometric relationship between the length of the bounding box and the actual length of the fish to calculate a more accurate estimation of fish body length. Experimental validation showcases the applicability of our measurement method to diverse fish species and substantiates its exceptional performance in both experimental and real-world scenarios. The maximum average relative errors for each group are within 8%, and the average relative error is 3.28% under the exact value constraints presented in the experiments. This method makes a significant contribution to fish length estimation and offers valuable insights for applications in fisheries and aquaculture.

A Novel Obstacle Traversal Method for Multiple Robotic Fish Based on Cross-Modal Variational Autoencoders and Imitation Learning.

Precision control of multiple robotic fish visual navigation in complex underwater environments has long been a challenging issue in the field of underwater robotics. To address this problem, this paper proposes a multi-robot fish obstacle traversal technique based on the combination of cross-modal variational autoencoder (CM-VAE) and imitation learning. Firstly, the overall framework of the robotic fish control system is introduced, where the first-person view of the robotic fish is encoded into a low-dimensional latent space using CM-VAE, and then different latent features in the space are mapped to the velocity commands of the robotic fish through imitation learning. Finally, to validate the effectiveness of the proposed method, experiments are conducted on linear, S-shaped, and circular gate frame trajectories with both single and multiple robotic fish. Analysis reveals that the visual navigation method proposed in this paper can stably traverse various types of gate frame trajectories. Compared to end-to-end learning and purely unsupervised image reconstruction, the proposed control strategy demonstrates superior performance, offering a new solution for the intelligent navigation of robotic fish in complex environments.

A novel multi-source navigation algorithm based on factor graph in complex underwater environments of polar regions

Autonomous underwater vehicle (AUV) is an unmanned, cableless, self-propelled, autonomous navigation and control vehicle that maneuvers under unmanned or minimally monitored and intervened conditions. To solve the problem of increasing navigation accuracy error caused by time-varying measurement noise of AUV auxiliary sensors in complex underwater environments of polar regions, a multi-source navigation algorithm for AUV based on improved factor graph is proposed. The algorithm first adds a confidence function to the standard factor graph algorithm, which is used to adjust the covariance matrix of the navigation sensor to suppress the problem of time-varying measurement noise. Then, a sliding window is added to the factor graph algorithm and only nodes within the sliding window are optimized to ensure real-time performance. Finally, considering that inertial navigation has high accuracy in a short period of time, inertial navigation iterations are performed on nodes that are about to be marginalized within the sliding window to improve navigation accuracy. The analyses of the simulation experiment results show that the algorithm can effectively cope with the time-varying problem of measurement noise and ensure the accuracy and robustness of the AUV navigation system in the complex marine environment.

AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection

In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection. AMSP-UOD specifically addresses the impact of non-ideal imaging factors on detection accuracy in complex underwater environments. To mitigate the influence of noise on object detection performance, we propose AMSP Vortex Convolution (AMSP-VConv) to disrupt the noise distribution, enhance feature extraction capabilities, effectively reduce parameters, and improve network robustness. We design the Feature Association Decoupling Cross Stage Partial (FAD-CSP) module, which strengthens the association of long and short range features, improving the network performance in complex underwater environments. Additionally, our sophisticated post-processing method, based on non-maximum suppression with aspect-ratio similarity thresholds, optimizes detection in dense scenes, such as waterweed and schools of fish, improving object detection accuracy. Extensive experiments on the URPC and RUOD datasets demonstrate that our method outperforms existing state-of-the-art methods in terms of accuracy and noise immunity. AMSP-UOD proposes an innovative solution with the potential for real-world applications. Our code is available at https://github.com/zhoujingchun03/AMSP-UOD.

Research on Underwater Image Enhancement Algorithm

In recent years, with the continuous expansion of human activity areas, the Marine pollution caused by human activities has become increasingly serious, and the large influx of agricultural emissions and household garbage needs to rely on underwater equipment to clean up. However, to identify garbage from the complex underwater environment, it is necessary to study the underwater image enhancement algorithm. Therefore, this paper takes underwater plastic floaters as the research object, starts with the optical imaging model of underwater images, analyzes the process and mechanism of underwater optical imaging, and its impact on image quality, so as to better understand the causes of image degradation. Based on white balance algorithm, histogram equalization algorithm, bilateral filter algorithm and gamma correction method, the underwater image recognition image is improved. The principle of these methods to enhance underwater image is analyzed and applied to further improve the effect of underwater image enhancement.

Bio-Inspired Cooperative Control Scheme of Obstacle Avoidance for UUV Swarm

The complex underwater environment poses significant challenges for unmanned underwater vehicles (UUVs), particularly in terms of communication constraints and the need for precise cooperative obstacle avoidance and trajectory tracking. Addressing these challenges solely through position information is crucial in this field. This study explores the intricate task of managing a group of UUVs as they navigate obstacles and follow a given trajectory, all based on position information. A new dynamic interactive topology framework utilizing sonar technology has been developed for the UUVs. This framework not only provides position information for the UUV swarm but also for the surrounding obstacles, enhancing situational awareness. Additionally, a bio-inspired cooperative control strategy designed for UUV swarms utilizing sonar interaction topology is introduced. This innovative method eliminates the need for velocity data from neighboring UUVs, instead relying solely on position information to achieve swarm cooperative control, obstacle avoidance, and trajectory adherence. The effectiveness of this method is validated through extensive simulations. The results show that the proposed method demonstrates improved sensitivity in obstacle detection, enabling faster trajectory tracking while maintaining a safer distance compared to traditional methods. Ultimately, this innovative strategy not only enhances operational efficiency but also enhances safety measures in UUV swarm operations.

Underwater Rescue Target Detection Based on Acoustic Images.

In order to effectively respond to floods and water emergencies that result in the drowning of missing persons, timely and effective search and rescue is a very critical step in underwater rescue. Due to the complex underwater environment and low visibility, unmanned underwater vehicles (UUVs) with sonar are more efficient than traditional manual search and rescue methods to conduct active searches using deep learning algorithms. In this paper, we constructed a sound-based rescue target dataset that encompasses both the source and target domains using deep transfer learning techniques. For the underwater acoustic rescue target detection of small targets, which lack image feature accuracy, this paper proposes a two-branch convolution module and improves the YOLOv5s algorithm model to design an acoustic rescue small target detection algorithm model. For an underwater rescue target dataset based on acoustic images with a small sample acoustic dataset, a direct fine-tuning using optical image pre-training lacks cross-domain adaptability due to the different statistical properties of optical and acoustic images. This paper therefore proposes a heterogeneous information hierarchical migration learning method. For the false detection of acoustic rescue targets in a complex underwater background, the network layer is frozen during the hierarchical migration of heterogeneous information to improve the detection accuracy. In addition, in order to be more applicable to the embedded devices carried by underwater UAVs, an underwater acoustic rescue target detection algorithm based on ShuffleNetv2 is proposed to improve the two-branch convolutional module and the backbone network of YOLOv5s algorithm, and to create a lightweight model based on hierarchical migration of heterogeneous information. Through extensive comparative experiments conducted on various acoustic images, we have thoroughly validated the feasibility and effectiveness of our method. Our approach has demonstrated state-of-the-art performance in underwater search and rescue target detection tasks.

Accurate Identification for CW Direct Signal in Underwater Acoustic Ranging

The underwater channel is bilateral, heterogeneous, uncertain, and exhibits multipath transmission, sound line curvature, etc. These properties complicate the structure of the received pulse, causing great challenges in direct signal identification for ranging purposes and impacts on back-end data processing, even accurate acoustic positioning. Machine learning (ML) combined with underwater acoustics has emerged as a prominent area of research in recent years. From a statistical perspective, ML can be viewed as an optimization strategy. Nevertheless, the existing ML-based direct-signal discrimination approaches rely on independent assessment, utilizing a single sensor (beacon or buoy), which is still insufficient for adapting to the complex underwater environment. Thus, discrimination accuracy decreases. To address the above issues, an accurate CW direct signal detection approach is performed using the decision tree algorithm, which belongs to ML. Initially, the pulse parameter characteristics in the underwater multipath channel are investigated and the parameter models are built. Then, based on multi-sensor localization performance feedback, fusion characteristics for diverse pulse are created. Next, the pulse parameter characteristics are preprocessed to mitigate the impact of varying magnitudes and units of magnitude on data processing. Then, the decision tree is built to obtain the desired output results and realize accurate recognition of the ranging direct signals. Finally, the feasibility and reliability of this paper’s method are verified by computer simulation and field testing.

Image enhancement-based detection of concrete cracks under turbid water bodies

ABSTRACT Underwater concrete structure crack detection and structural health condition assessment based on image processing is challenging. The complex underwater environment and severe image degradation seriously affect the accuracy of crack detection. To solve these problems, a monocular vision and image-enhanced fractal-based fractal science based on computer vision and image processing techniques are proposed to conduct a non-contact detection study of underwater concrete cracks. This study established a four-level structural health condition to assist in underwater crack measurement and safety assessment. The box-counting method was used as a practical tool to calculate the fractal dimension. Three distances of 0.5, 0.8, and 1.2 m were set to verify the effective distance of the algorithm. The results show that the method proposed in this study can effectively detect cracks in submerged concrete members within 0.6 m and help managers correctly determine the structure's health using the fractal dimension.

Acoustic scattering characteristics of underwater buried oil pipeline

With the development of offshore oil resources, subsea oil pipelines have emerged. As a fast, economical, and safe way to transport oil resources, subsea pipelines are known as the “lifeline” of offshore oil projects. However, the detection of submarine pipelines is very difficult due to the complex underwater environment. One of the mainstream methods to detect submarine pipelines is the employment of sonar. Hence, the acoustic scattering characteristics of submarine pipelines play an important role in detecting themselves. In this study, the acoustic scattering model of the buried pipeline is established using the finite element method, and the scattering mechanism of the buried pipeline is analyzed. The effects of different frequencies, grazing angles, burial depth, and other factors on the acoustic scattering characteristics of the buried pipeline are investigated, providing the reference significance for detecting submarine pipelines.

COC-UFGAN: Underwater image enhancement based on color opponent compensation and dual-subnet underwater fusion generative adversarial network

Due to the complex underwater environment and the attenuation of light, the underwater image is produced with various distortions such as color loss, low contrast, noise, blur, and haze-like, which bring significant challenges to underwater image applications. To alleviate these problems, a novel color opponent compensation and a dual-subnet underwater fusion generative adversarial network (COC-UFGAN) are proposed by simulating the information processing mechanism in the human visual system (HVS). Specifically, considering the color opponent mechanism of the primary visual cortex and the characteristics of underwater imaging, an opponent domain is constructed consisting of four color opponent channels: green–red, yellow-blue, cyan-red and black-white. Then, a novel local-to-global color opponent compensation method is designed to restore color loss in underwater imaging. Furthermore, considering the complexity of underwater imaging, a dual-subnet underwater fusion generative adversarial network is designed. Finally, experimental results on synthetic and natural underwater images demonstrate the superiority of the proposed COC-UFGAN over the state-of-the-art methods qualitatively and quantitatively.

Uncertainty Quantification of Neural Reflectance Fields for Underwater Scenes

Neural radiance fields and neural reflectance fields are novel deep learning methods for generating novel views of 3D scenes from 2D images. To extend the neural scene representation techniques to complex underwater environments, beyond neural reflectance fields underwater (BNU) was proposed, which considers the relighting conditions of on-aboard light sources by using neural reflectance fields, and approximates the attenuation and backscatter effects of water with an additional constant. Because the quality of the neural representation of underwater scenes is critical to downstream tasks such as marine surveying and mapping, the model reliability should be considered and evaluated. However, current neural reflectance models lack the ability of quantifying the uncertainty of underwater scenes that are not directly observed during training, which hinders their widespread use in the field of underwater unmanned autonomous navigation. To address this issue, we introduce an ensemble strategy to BNU that quantifies cognitive uncertainty in color space and unobserved regions with the expectation and variance of RGB values and termination probabilities along the ray. We also employ a regularization method to smooth the density of the underwater neural reflectance model. The effectiveness of the present method is demonstrated in numerical experiments.

An on-line weld inspection method for underwater offshore structure based on an improved deep convolutional network

ABSTRACT The acoustic signal analysing is a crucial evaluation method for welding repair of in-service marine structures. However, the complex underwater environment complicates the quality evaluations. In addition, the weak acoustic signal poses challenges for traditional methods during signal processing, such as low signal-to-noise ratio and difficulty in feature extraction. In this paper, an improved deep convolutional network method for online weld inspection of underwater offshore structures is proposed. First, a Variational Mode Decomposition (VMD) algorithm is used to extract weak signals. The raw acoustic signal is denoised, and the effective pulses are extracted. Next, the recurrence and gradient plot methods are applied to extract the pulse features and to generate corresponding images. Finally, a VGG16 deep convolutional network is used to classify image samples and determine weld quality online. Results indicate that the VMD algorithm can process and reduce noise, the recurrence and gradient plot provide quality related image features for the neural network. The VGG16 neural network outperforms the VGG19, RESNET34, and RESNET50 neural networks and can achieve a 97.5% recognition rate. This paper offers some avenues for online identification of weld quality in underwater welding.

Super-resolution reconstruction of underwater polarized images with a fused attention mechanism.

The polarization imaging technique leverages the disparity between target and background polarization information to mitigate the impact of backward scattered light, thereby enhancing image quality. However, the imaging model of this method exhibits limitations in extracting inter-image features, resulting in less-than-optimal outcomes in turbid underwater environments. In recent years, machine learning methodologies, particularly neural networks, have gained traction. These networks, renowned for their superior fitting capabilities, can effectively extract information from multiple images. The incorporation of an attention mechanism significantly augments the capacity of neural networks to extract inter-image correlation attributes, thereby mitigating the constraints of polarization imaging methods to a certain degree. To enhance the efficacy of polarization imaging in complex underwater environments, this paper introduces a super-resolution network with an integrated attention mechanism, termed as SRGAN-DP. This network is a fusion of an enhanced SRGAN network and the high-performance deep pyramidal split attention (DPSA) module, also proposed in this paper. SRGAN-DP is employed to perform high-resolution reconstruction of the underwater polarimetric image dataset, constructed specifically for this study. A comparative analysis with existing algorithms demonstrates that our proposed algorithm not only produces superior images but also exhibits robust performance in real-world environments.